diff options
Diffstat (limited to 'tools/perf/bench/futex-wake-parallel.c')
-rw-r--r-- | tools/perf/bench/futex-wake-parallel.c | 143 |
1 files changed, 84 insertions, 59 deletions
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index cd2b81a845ac..b66df553e561 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -10,6 +10,7 @@ #include "bench.h" #include <linux/compiler.h> #include "../util/debug.h" +#include "../util/mutex.h" #ifndef HAVE_PTHREAD_BARRIER int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe_unused) @@ -29,12 +30,12 @@ int bench_futex_wake_parallel(int argc __maybe_unused, const char **argv __maybe #include <linux/time64.h> #include <errno.h> #include "futex.h" -#include <internal/cpumap.h> #include <perf/cpumap.h> #include <err.h> #include <stdlib.h> #include <sys/time.h> +#include <sys/mman.h> struct thread_data { pthread_t worker; @@ -48,20 +49,23 @@ static unsigned int nwakes = 1; static u_int32_t futex = 0; static pthread_t *blocked_worker; -static bool done = false, silent = false, fshared = false; -static unsigned int nblocked_threads = 0, nwaking_threads = 0; -static pthread_mutex_t thread_lock; -static pthread_cond_t thread_parent, thread_worker; +static bool done = false; +static struct mutex thread_lock; +static struct cond thread_parent, thread_worker; static pthread_barrier_t barrier; static struct stats waketime_stats, wakeup_stats; static unsigned int threads_starting; static int futex_flag = 0; +static struct bench_futex_parameters params; + static const struct option options[] = { - OPT_UINTEGER('t', "threads", &nblocked_threads, "Specify amount of threads"), - OPT_UINTEGER('w', "nwakers", &nwaking_threads, "Specify amount of waking threads"), - OPT_BOOLEAN( 's', "silent", &silent, "Silent mode: do not display data/details"), - OPT_BOOLEAN( 'S', "shared", &fshared, "Use shared futexes instead of private ones"), + OPT_UINTEGER('t', "threads", ¶ms.nthreads, "Specify amount of threads"), + OPT_UINTEGER('w', "nwakers", ¶ms.nwakes, "Specify amount of waking threads"), + OPT_BOOLEAN( 's', "silent", ¶ms.silent, "Silent mode: do not display data/details"), + OPT_BOOLEAN( 'S', "shared", ¶ms.fshared, "Use shared futexes instead of private ones"), + OPT_BOOLEAN( 'm', "mlockall", ¶ms.mlockall, "Lock all current and future memory"), + OPT_END() }; @@ -91,16 +95,18 @@ static void *waking_workerfn(void *arg) return NULL; } -static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr) +static void wakeup_threads(struct thread_data *td) { unsigned int i; + pthread_attr_t thread_attr; + pthread_attr_init(&thread_attr); pthread_attr_setdetachstate(&thread_attr, PTHREAD_CREATE_JOINABLE); - pthread_barrier_init(&barrier, NULL, nwaking_threads + 1); + pthread_barrier_init(&barrier, NULL, params.nwakes + 1); /* create and block all threads */ - for (i = 0; i < nwaking_threads; i++) { + for (i = 0; i < params.nwakes; i++) { /* * Thread creation order will impact per-thread latency * as it will affect the order to acquire the hb spinlock. @@ -113,21 +119,22 @@ static void wakeup_threads(struct thread_data *td, pthread_attr_t thread_attr) pthread_barrier_wait(&barrier); - for (i = 0; i < nwaking_threads; i++) + for (i = 0; i < params.nwakes; i++) if (pthread_join(td[i].worker, NULL)) err(EXIT_FAILURE, "pthread_join"); pthread_barrier_destroy(&barrier); + pthread_attr_destroy(&thread_attr); } static void *blocked_workerfn(void *arg __maybe_unused) { - pthread_mutex_lock(&thread_lock); + mutex_lock(&thread_lock); threads_starting--; if (!threads_starting) - pthread_cond_signal(&thread_parent); - pthread_cond_wait(&thread_worker, &thread_lock); - pthread_mutex_unlock(&thread_lock); + cond_signal(&thread_parent); + cond_wait(&thread_worker, &thread_lock); + mutex_unlock(&thread_lock); while (1) { /* handle spurious wakeups */ if (futex_wait(&futex, 0, NULL, futex_flag) != EINTR) @@ -138,25 +145,39 @@ static void *blocked_workerfn(void *arg __maybe_unused) return NULL; } -static void block_threads(pthread_t *w, pthread_attr_t thread_attr, - struct perf_cpu_map *cpu) +static void block_threads(pthread_t *w, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; + + threads_starting = params.nthreads; - threads_starting = nblocked_threads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); /* create and block all threads */ - for (i = 0; i < nblocked_threads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(cpu->map[i % cpu->nr], &cpuset); + for (i = 0; i < params.nthreads; i++) { + pthread_attr_t thread_attr; + + pthread_attr_init(&thread_attr); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } + pthread_attr_destroy(&thread_attr); } + CPU_FREE(cpuset); } static void print_run(struct thread_data *waking_worker, unsigned int run_num) @@ -168,7 +189,7 @@ static void print_run(struct thread_data *waking_worker, unsigned int run_num) init_stats(&__wakeup_stats); init_stats(&__waketime_stats); - for (i = 0; i < nwaking_threads; i++) { + for (i = 0; i < params.nwakes; i++) { update_stats(&__waketime_stats, waking_worker[i].runtime.tv_usec); update_stats(&__wakeup_stats, waking_worker[i].nwoken); } @@ -179,7 +200,7 @@ static void print_run(struct thread_data *waking_worker, unsigned int run_num) printf("[Run %d]: Avg per-thread latency (waking %d/%d threads) " "in %.4f ms (+-%.2f%%)\n", run_num + 1, wakeup_avg, - nblocked_threads, waketime_avg / USEC_PER_MSEC, + params.nthreads, waketime_avg / USEC_PER_MSEC, rel_stddev_stats(waketime_stddev, waketime_avg)); } @@ -194,7 +215,7 @@ static void print_summary(void) printf("Avg per-thread latency (waking %d/%d threads) in %.4f ms (+-%.2f%%)\n", wakeup_avg, - nblocked_threads, + params.nthreads, waketime_avg / USEC_PER_MSEC, rel_stddev_stats(waketime_stddev, waketime_avg)); } @@ -204,7 +225,7 @@ static void do_run_stats(struct thread_data *waking_worker) { unsigned int i; - for (i = 0; i < nwaking_threads; i++) { + for (i = 0; i < params.nwakes; i++) { update_stats(&waketime_stats, waking_worker[i].runtime.tv_usec); update_stats(&wakeup_stats, waking_worker[i].nwoken); } @@ -223,7 +244,6 @@ int bench_futex_wake_parallel(int argc, const char **argv) int ret = 0; unsigned int i, j; struct sigaction act; - pthread_attr_t thread_attr; struct thread_data *waking_worker; struct perf_cpu_map *cpu; @@ -239,87 +259,92 @@ int bench_futex_wake_parallel(int argc, const char **argv) act.sa_sigaction = toggle_done; sigaction(SIGINT, &act, NULL); - cpu = perf_cpu_map__new(NULL); + if (params.mlockall) { + if (mlockall(MCL_CURRENT | MCL_FUTURE)) + err(EXIT_FAILURE, "mlockall"); + } + + cpu = perf_cpu_map__new_online_cpus(); if (!cpu) err(EXIT_FAILURE, "calloc"); - if (!nblocked_threads) - nblocked_threads = cpu->nr; + if (!params.nthreads) + params.nthreads = perf_cpu_map__nr(cpu); /* some sanity checks */ - if (nwaking_threads > nblocked_threads || !nwaking_threads) - nwaking_threads = nblocked_threads; + if (params.nwakes > params.nthreads || + !params.nwakes) + params.nwakes = params.nthreads; - if (nblocked_threads % nwaking_threads) + if (params.nthreads % params.nwakes) errx(EXIT_FAILURE, "Must be perfectly divisible"); /* * Each thread will wakeup nwakes tasks in * a single futex_wait call. */ - nwakes = nblocked_threads/nwaking_threads; + nwakes = params.nthreads/params.nwakes; - blocked_worker = calloc(nblocked_threads, sizeof(*blocked_worker)); + blocked_worker = calloc(params.nthreads, sizeof(*blocked_worker)); if (!blocked_worker) err(EXIT_FAILURE, "calloc"); - if (!fshared) + if (!params.fshared) futex_flag = FUTEX_PRIVATE_FLAG; printf("Run summary [PID %d]: blocking on %d threads (at [%s] " "futex %p), %d threads waking up %d at a time.\n\n", - getpid(), nblocked_threads, fshared ? "shared":"private", - &futex, nwaking_threads, nwakes); + getpid(), params.nthreads, params.fshared ? "shared":"private", + &futex, params.nwakes, nwakes); init_stats(&wakeup_stats); init_stats(&waketime_stats); - pthread_attr_init(&thread_attr); - pthread_mutex_init(&thread_lock, NULL); - pthread_cond_init(&thread_parent, NULL); - pthread_cond_init(&thread_worker, NULL); + mutex_init(&thread_lock); + cond_init(&thread_parent); + cond_init(&thread_worker); for (j = 0; j < bench_repeat && !done; j++) { - waking_worker = calloc(nwaking_threads, sizeof(*waking_worker)); + waking_worker = calloc(params.nwakes, sizeof(*waking_worker)); if (!waking_worker) err(EXIT_FAILURE, "calloc"); /* create, launch & block all threads */ - block_threads(blocked_worker, thread_attr, cpu); + block_threads(blocked_worker, cpu); /* make sure all threads are already blocked */ - pthread_mutex_lock(&thread_lock); + mutex_lock(&thread_lock); while (threads_starting) - pthread_cond_wait(&thread_parent, &thread_lock); - pthread_cond_broadcast(&thread_worker); - pthread_mutex_unlock(&thread_lock); + cond_wait(&thread_parent, &thread_lock); + cond_broadcast(&thread_worker); + mutex_unlock(&thread_lock); usleep(100000); /* Ok, all threads are patiently blocked, start waking folks up */ - wakeup_threads(waking_worker, thread_attr); + wakeup_threads(waking_worker); - for (i = 0; i < nblocked_threads; i++) { + for (i = 0; i < params.nthreads; i++) { ret = pthread_join(blocked_worker[i], NULL); if (ret) err(EXIT_FAILURE, "pthread_join"); } do_run_stats(waking_worker); - if (!silent) + if (!params.silent) print_run(waking_worker, j); free(waking_worker); } /* cleanup & report results */ - pthread_cond_destroy(&thread_parent); - pthread_cond_destroy(&thread_worker); - pthread_mutex_destroy(&thread_lock); - pthread_attr_destroy(&thread_attr); + cond_destroy(&thread_parent); + cond_destroy(&thread_worker); + mutex_destroy(&thread_lock); print_summary(); free(blocked_worker); + perf_cpu_map__put(cpu); return ret; } #endif /* HAVE_PTHREAD_BARRIER */ |